INDEX

Explanations

locations and descriptions of scenes or objects

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 hairc

-0.93

Lma

-0.89

Lmfao

-0.89

 Darum

-0.87

Fuckin

-0.86

 Souha

-0.86

 Endlich

-0.86

 notor

-0.86

 suspic

-0.84

FTFY

-0.82

POSITIVE LOGITS

 There

0.70

It

0.69

 They

0.68

 This

0.64

 Then

0.63

The

0.61

 These

0.60

An

0.59

Its

0.58

 ***!

0.58

Activations Density 0.491%

locations and descriptions of scenes or objects

No Comments

No Known Activations